Deep Learning Solution For Pathological Voice Detection Using Lstm-Based Autoencoder Hybrid With Multi-Task Learning

BIOSIGNALS: PROCEEDINGS OF THE 14TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES - VOL 4: BIOSIGNALS(2021)

引用 11|浏览0
暂无评分
摘要
In this paper, a deep learning approach is introduced to detect pathological voice disorders from continuous speech. Speech as bio-signal is getting more and more attention as a discriminant for different diseases. To exploit information in speech, a long-short term memory (LSTM) autoencoder hybrid with multi-task learning solution is proposed with spectrogram as input feature. Different speech databases (voice disorders, depression, Parkinson's disease) are applied as evaluation datasets. Applicability of the method is demonstrated by obtaining accuracies 85% for Parkinson's disease, 86% for dysphonia, and 90% for depression on test datasets. The advantage of this method is that it is fully data-driven, in the sense that it does not require special acoustic-phonetic preprocessing separately for the types of disease to be recognized. We believe that the applied method in this article can be used to other diseases as well and can be used for other languages also.
更多
查看译文
关键词
Deep Neural Networks, Long-Short Term Memory, Autoencoder, Multi-Task Learning, Speech, Bio-signal, LSTM, Voice Pathologies, Parkinson, Depression
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要